Pwning machine learning systems - Octavius 6

Pwning machine learning systems - Octavius 6

Actions and Detail Panel

Sales Ended

Date and time


Caesars Palace

Paradise, NV 89109

View map


Pwning machine learning systems

Instructors: Clarence Chio & Anto Joseph

Pre-Requisites - Basic familiarity with Linux and Python scripting knowledge is a plus, but not essential

Abstract - Pwning machine learning systems is an offensive-focused workshop that gives attendees a whirlwind introduction to the world of adversarial machine learning. This three-hour workshop will not be your run-of-the-mill introduction to machine learning course, (are you kidding? you can get that from a thousand different places online!) but will focus on hands-on examples, and actually attacking these systems. Every concept covered in this workshop will be backed-up with either a worked example or a challenge activity, (done in groups of 1 to 3) with minimal lecturing and maximum "doing". By the end of the workshop, students will be able to confidently pwn machine-learning-powered malware classifiers, intrusion detectors, and WAFs. We will cover the three major kinds of attacks on machine learning and deep learning systems - model poisoning, adversarial generation, and reinforcement learning attacks. As a bonus, attendees will emerge from the session with a fully-upgraded machine learning B.S. detector, giving them the ability to call B.S. on any "next-generation system" that claims to be impenetrable because of machine learning.

This is an intermediate technical class suitable for attendees with some ability to read and write basic Python code. To get the most out of this workshop, surface-level understanding of machine learning is good. (be able to give a one-line answer to the question "What is machine learning?")

Required Materials -

  • latest version of virtualbox Installed

  • administrative access on your laptop with external USB allowed

  • at least 20 GB free hard disk space

  • at least 4 GB RAM (the more the merrier)

Save This Event

Event Saved